Resonance Frequency Estimation for Equilateral Triangular Microstrip Antennas Using Artificial Neural Network Model

Neural Network modeling as computational tool has been widely used in many practical problems in the field of communication. This paper proposes the use of neural network modeling to microstrip antenna. The same has been developed for equilateral triangular microstrip antenna which is used on suspended air as well as glass epoxy suspended substrates. Using proposed model, frequencies calculated over wide range and for increasing substrate thickness give closer agreement with the simulated data obtained using IE3D simulations. At some frequencies and substrate thickness, measurements have also been carried out to validate the proposed model. A good agreement between simulated, measured, and calculated results is observed with % error of less than 2%.